ABSTRACT
Proteins play a variety of functional roles in cellular activities and are indispensable for life. Understanding the functions of proteins is crucial in many fields such as medicine and drug development. In addition, the application of enzymes in green synthesis has been of great interest, but the high cost of obtaining specific functional enzymes as well as the variety of enzyme types and functions hamper their application. At present, the specific functions of proteins are mainly determined through tedious and time-consuming experimental characterization. With the rapid development of bioinformatics and sequencing technologies, the number of protein sequences that have been sequenced is much larger than those can be annotated, thus developing efficient methods for predicting protein functions becomes crucial. With the rapid development of computer technology, data-driven machine learning methods have become a promising solution to these challenges. This review provides an overview of protein function and its annotation methods as well as the development history and operation process of machine learning. In combination with the application of machine learning in the field of enzyme function prediction, we present an outlook on the future direction of efficient artificial intelligence-assisted protein function research.
Subject(s)
Artificial Intelligence , Machine Learning , Proteins/genetics , Computational Biology/methods , Drug DevelopmentABSTRACT
Objective:To study the immunotherapy effects of different doses of human peripheral blood γδT cells on human hepatoma cells (SMMC-7721) xenograft model.Methods: (1)The nude mouse model of liver cancer was established by inoculated BALB/c mouse subcutaneous with human hepatoma cell line (SMMC-7721).(2)The mononuclear cells in healthy human were extracted from peripheral blood,and specific amplification γδT cells in vitro.(3) The nude mouse model divided into 5 groups by random.The positive control group was 5-Fu,negative control group was normal saline(NS).The treatment group was injected different doses of γδT cells(1×105,5×105 and 25×105)by nude mice tail vein.The positive control group injected 5-Fu by enterocoelia,negative control group injected NS by tail veins.The inhibition effect of different dose γδT cells on tumor was observed,including weight,food intake and growth conditions,etc.and the changes of tumor volume (TV),relative tumor volume (RTV)and relative tumor appreciation rate[T/C(%)] were compared with positive control group and negative control group.Results: Different dose of γδT cells had different degree of inhibition on nude mouse xenograft growth.RTV compared with saline negative control group was statistically significant (P<0.05).Compared with the positive control group of 5-Fu,the TV growth was significantly lower than the 5-Fu,degree of inhibition was similar in RTV each dose group,and all slightly higher than the 5-Fu positive control group.The each dose group of T/C (%)was slightly lower than the relative tumor proliferation rate of the control group of 5-Fu,but had no significant difference.Conclusion: The γδT cells from peripheral blood had significant inhibitory effect on nude mice transplanted liver tumor and it may be used as a new treatment for liver cancer immunotherapy provide experimental data.